Find, test and add skills at no cost. Paid plans add publishing, more usage, more seats and longer history.
Start free — the whole skills registry, router, and safety scan, plus your first agent.
Go from using skills to publishing them, with a team of 5 and private analytics.
Run skills in production at scale: 10× the traces and 25 seats.
Unlimited scale, with an org-private registry, SSO and an SLA.
The 15 differences that decide a plan: the limits and features where the numbers jump, skills first.
One end-to-end agent run, however many LLM calls and tool calls it contains. We meter runs, not tokens.
Nothing breaks. Ingest pauses at the cap and resumes next cycle, or upgrade in one click. We never silently bill overages.
Yes. Downgrades take effect at the end of the billing cycle, and your data stays exportable on every plan.
Yes. The SDK, CLI and static safety scan are MIT licensed, and the eval runner is Apache-2.0, free to fork and run on any plan. Paid plans cover hosted scale, publishing and support.